Design of a novel noise resilient algorithm for fault detection in wind turbines on supervisory control and data acquisition system

Abstract Wind turbine faults, including electrical, mechanical or aerodynamics-related, can potentially reduce operational efficiency, causing downtimes or, in some cases, leading to severe damage. Hence, timely detection of these operational anomalies is crucial for optimizing performance and reduc...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Irfan, Nabeel Ahmed Khan, Muhammad Abubakar, Zohaib Mushtaq, Tomasz Jakubowski, Paweł Sokołowski, Grzegorz Nawalany, Saifur Rahman
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-97663-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850146267748892672
author Muhammad Irfan
Nabeel Ahmed Khan
Muhammad Abubakar
Zohaib Mushtaq
Tomasz Jakubowski
Paweł Sokołowski
Grzegorz Nawalany
Saifur Rahman
author_facet Muhammad Irfan
Nabeel Ahmed Khan
Muhammad Abubakar
Zohaib Mushtaq
Tomasz Jakubowski
Paweł Sokołowski
Grzegorz Nawalany
Saifur Rahman
author_sort Muhammad Irfan
collection DOAJ
description Abstract Wind turbine faults, including electrical, mechanical or aerodynamics-related, can potentially reduce operational efficiency, causing downtimes or, in some cases, leading to severe damage. Hence, timely detection of these operational anomalies is crucial for optimizing performance and reducing maintenance costs. The following study explores the application of Supervisory Control and Data Acquisition (SCADA) data for fault detection and diagnosing different operational states in wind turbines by focusing on environmental and operational factors which affect the performance. An efficient noise-resilient classification framework is proposed which includes a novel Perturbed-Random Forest (P-RF) algorithm to diagnose operational states with high accuracy even under noisy conditions. Seasonal discrepancies in power generation are analyzed using theoretical and actual power analysis. Further, distributions of features are realized via kernel density estimation and efficiency metrics in order to identify performance inefficiencies. The P-RF algorithm achieved 99.72% accuracy in diagnosing the status of the SCADA-based wind turbine although with a slightly higher computational complexity than a baseline Random Forest algorithm. Multiple Evaluation metrics were employed to assess the performance of the proposed model under different signal-to-noise conditions.
format Article
id doaj-art-2b190b2784794a54bbdcf1a8faa89d3b
institution OA Journals
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-2b190b2784794a54bbdcf1a8faa89d3b2025-08-20T02:27:53ZengNature PortfolioScientific Reports2045-23222025-04-0115111910.1038/s41598-025-97663-3Design of a novel noise resilient algorithm for fault detection in wind turbines on supervisory control and data acquisition systemMuhammad Irfan0Nabeel Ahmed Khan1Muhammad Abubakar2Zohaib Mushtaq3Tomasz Jakubowski4Paweł Sokołowski5Grzegorz Nawalany6Saifur Rahman7Electrical Engineering Department, College of Engineering, Najran UniversityCenter for AI & Big Data, Namal UniversityDepartment of Computer Science, Lahore Garrison UniversityDepartment of Electrical Electronics and Computer Systems, College of Engineering and Technology, University of SargodhaDepartment of Machine Operation, Ergonomics and Production Processes, Faculty of Production and Power Engineering, University of Agriculture in KrakowDepartment of Rural Building, Faculty of Environmental Engineering and Land Surveying, University of Agriculture in KrakowDepartment of Rural Building, Faculty of Environmental Engineering and Land Surveying, University of Agriculture in KrakowElectrical Engineering Department, College of Engineering, Najran UniversityAbstract Wind turbine faults, including electrical, mechanical or aerodynamics-related, can potentially reduce operational efficiency, causing downtimes or, in some cases, leading to severe damage. Hence, timely detection of these operational anomalies is crucial for optimizing performance and reducing maintenance costs. The following study explores the application of Supervisory Control and Data Acquisition (SCADA) data for fault detection and diagnosing different operational states in wind turbines by focusing on environmental and operational factors which affect the performance. An efficient noise-resilient classification framework is proposed which includes a novel Perturbed-Random Forest (P-RF) algorithm to diagnose operational states with high accuracy even under noisy conditions. Seasonal discrepancies in power generation are analyzed using theoretical and actual power analysis. Further, distributions of features are realized via kernel density estimation and efficiency metrics in order to identify performance inefficiencies. The P-RF algorithm achieved 99.72% accuracy in diagnosing the status of the SCADA-based wind turbine although with a slightly higher computational complexity than a baseline Random Forest algorithm. Multiple Evaluation metrics were employed to assess the performance of the proposed model under different signal-to-noise conditions.https://doi.org/10.1038/s41598-025-97663-3Perturbed-Random forestSupervisory controlData acquisitionKernel densityWind turbineFault detection
spellingShingle Muhammad Irfan
Nabeel Ahmed Khan
Muhammad Abubakar
Zohaib Mushtaq
Tomasz Jakubowski
Paweł Sokołowski
Grzegorz Nawalany
Saifur Rahman
Design of a novel noise resilient algorithm for fault detection in wind turbines on supervisory control and data acquisition system
Scientific Reports
Perturbed-Random forest
Supervisory control
Data acquisition
Kernel density
Wind turbine
Fault detection
title Design of a novel noise resilient algorithm for fault detection in wind turbines on supervisory control and data acquisition system
title_full Design of a novel noise resilient algorithm for fault detection in wind turbines on supervisory control and data acquisition system
title_fullStr Design of a novel noise resilient algorithm for fault detection in wind turbines on supervisory control and data acquisition system
title_full_unstemmed Design of a novel noise resilient algorithm for fault detection in wind turbines on supervisory control and data acquisition system
title_short Design of a novel noise resilient algorithm for fault detection in wind turbines on supervisory control and data acquisition system
title_sort design of a novel noise resilient algorithm for fault detection in wind turbines on supervisory control and data acquisition system
topic Perturbed-Random forest
Supervisory control
Data acquisition
Kernel density
Wind turbine
Fault detection
url https://doi.org/10.1038/s41598-025-97663-3
work_keys_str_mv AT muhammadirfan designofanovelnoiseresilientalgorithmforfaultdetectioninwindturbinesonsupervisorycontrolanddataacquisitionsystem
AT nabeelahmedkhan designofanovelnoiseresilientalgorithmforfaultdetectioninwindturbinesonsupervisorycontrolanddataacquisitionsystem
AT muhammadabubakar designofanovelnoiseresilientalgorithmforfaultdetectioninwindturbinesonsupervisorycontrolanddataacquisitionsystem
AT zohaibmushtaq designofanovelnoiseresilientalgorithmforfaultdetectioninwindturbinesonsupervisorycontrolanddataacquisitionsystem
AT tomaszjakubowski designofanovelnoiseresilientalgorithmforfaultdetectioninwindturbinesonsupervisorycontrolanddataacquisitionsystem
AT pawełsokołowski designofanovelnoiseresilientalgorithmforfaultdetectioninwindturbinesonsupervisorycontrolanddataacquisitionsystem
AT grzegorznawalany designofanovelnoiseresilientalgorithmforfaultdetectioninwindturbinesonsupervisorycontrolanddataacquisitionsystem
AT saifurrahman designofanovelnoiseresilientalgorithmforfaultdetectioninwindturbinesonsupervisorycontrolanddataacquisitionsystem